semantica/pyproject.toml

[build-system]
requires = ["setuptools>=61.0", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "semantica"
version = "0.1.1"
description = "🧠 Semantica - An Open Source Framework for building Semantic Layers and Knowledge Engineering "
readme = "README.md"
license = {text = "MIT"}
authors = [
    {name = "Hawksight AI", email = "semantica-dev@users.noreply.github.com"}
]
maintainers = [
    {name = "Hawksight AI", email = "semantica-dev@users.noreply.github.com"}
]
requires-python = ">=3.8"
classifiers = [
    "Development Status :: 3 - Alpha",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.8",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Software Development :: Libraries :: Python Modules",
    "Topic :: Text Processing :: Linguistic",
    "Topic :: Database :: Database Engines/Servers",
    "Topic :: Internet :: WWW/HTTP :: Indexing/Search"
]
keywords = [
    "semantic-layer", "knowledge-engineering", "nlp", "knowledge-graph",
    "embeddings", "entity-extraction", "relationship-extraction", "rdf",
    "ontology", "semantic-analysis", "ai", "machine-learning"
]
dependencies = [
    "numpy>=1.21.0",
    "pandas>=1.3.0",
    "scikit-learn>=1.0.0",
    "umap-learn>=0.5.0",
    "spacy>=3.4.0",
    "transformers>=4.20.0",
    "torch>=1.12.0",
    "sentence-transformers>=2.2.0",
    "rdflib>=6.2.0",
    "networkx>=2.8.0",
    "matplotlib>=3.5.0",
    "seaborn>=0.11.0",
    "plotly>=5.10.0",
    "ipywidgets>=8.0.0",
    "requests>=2.28.0",
    "GitPython>=3.1.30",
    "chardet>=5.1.0",
    "protobuf==4.25.8",
    "grpcio==1.67.1",
    "beautifulsoup4>=4.11.0",
    "lxml>=4.9.0",
    "pypdf2>=2.10.0",
    "python-docx>=0.8.11",
    "docling>=1.0.0",
    "openpyxl>=3.0.10",
    "pillow>=9.2.0",
    "librosa>=0.9.0",
    "opencv-python>=4.6.0",
    "faiss-cpu>=1.7.0",
    "fastembed>=0.2.0",
    "onnxruntime>=1.17.0",
    "tokenizers>=0.15.0",
    "weaviate-client>=3.15.0",
    "qdrant-client>=1.3.0",
    "neo4j>=5.0.0",
    "falkordb>=1.0.0",
    "pymongo>=4.2.0",
    "sqlalchemy>=1.4.0",
    "psycopg2-binary>=2.9.0",
    "pymysql>=1.0.0",
    "redis>=4.3.0",
    "celery>=5.2.0",
    "kafka-python>=2.0.0",
    "pulsar-client>=3.0.0",
    "pika>=1.3.0",
    "boto3>=1.24.0",
    "azure-storage-blob>=12.12.0",
    "google-cloud-storage>=2.5.0",
    "pydantic>=2.0.0",
    "fastmcp>=0.1.0",
    "groq>=0.4.0",
    "openai>=1.0.0",
    "litellm>=1.0.0",
    "instructor>=1.0.0",
    "click>=8.1.0",
    "rich>=12.5.0",
    "tqdm>=4.64.0",
    "pyyaml>=6.0",
    "toml>=0.10.0",
    "python-dotenv>=0.20.0",
    "loguru>=0.6.0",
    "structlog>=22.1.0",
    "prometheus-client>=0.14.0",
    "opentelemetry-api>=1.12.0",
    "opentelemetry-sdk>=1.12.0",
    "opentelemetry-instrumentation",
    "fastapi>=0.78.0",
    "uvicorn>=0.18.0",
    "pytest>=7.1.0",
    "pytest-cov>=3.0.0",
    "pytest-asyncio>=0.19.0",
    "black>=22.6.0",
    "isort>=5.10.0",
    "flake8>=4.0.0",
    "mypy>=0.971",
    "pre-commit>=2.19.0"
]
[project.urls]
Homepage = "https://github.com/Hawksight-AI/semantica"
Repository = "https://github.com/Hawksight-AI/semantica"
"Bug Tracker" = "https://github.com/Hawksight-AI/semantica/issues"
Discussions = "https://github.com/Hawksight-AI/semantica/discussions"

[project.optional-dependencies]
dev = [
    "pytest>=7.1.0",
    "pytest-cov>=3.0.0",
    "pytest-asyncio>=0.19.0",
    "black>=22.6.0",
    "isort>=5.10.0",
    "flake8>=4.0.0",
    "mypy>=0.971",
    "pre-commit>=2.19.0",
    "jupyter>=1.0.0",
    "ipykernel>=6.15.0",
    "notebook>=6.4.0"
]
viz = [
    "pyvis>=0.3.0",
    "graphviz>=0.20.0",
    "umap-learn>=0.5.0",
    "d3blocks>=1.0.0"
]
gpu = [
    "torch>=1.12.0",
    "faiss-gpu>=1.7.0",
    "cupy>=10.0.0"
]
cloud = [
    "boto3>=1.24.0",
    "azure-storage-blob>=12.12.0",
    "google-cloud-storage>=2.5.0",
    "kubernetes>=24.0.0",
    "helm>=3.10.0"
]
monitoring = [
    "prometheus-client>=0.14.0",
    "opentelemetry-api>=1.12.0",
    "opentelemetry-sdk>=1.12.0",
    "opentelemetry-instrumentation>=0.32.0",
    "grafana-api>=1.0.0",
    "elasticsearch>=8.5.0"
]
llm-openai = [
    "openai>=1.0.0"
]
llm-gemini = [
    "google-generativeai>=0.3.0"
]
llm-groq = [
    "groq>=0.4.0"
]
llm-anthropic = [
    "anthropic>=0.18.0"
]
llm-ollama = [
    "ollama>=0.1.0"
]
llm-deepseek = [
    "deepseek>=0.1.0"
]
llm-litellm = [
    "litellm>=1.0.0"
]
llm-instructor = [
    "instructor>=1.0.0"
]
llm-all = [
    "semantica[llm-openai,llm-gemini,llm-groq,llm-anthropic,llm-ollama,llm-deepseek,llm-litellm,llm-instructor]"
]
models-huggingface = [
    "transformers>=4.20.0",
    "torch>=1.12.0"
]
split-tiktoken = [
    "tiktoken>=0.5.0"
]
split-community = [
    "python-louvain>=0.16"
]
split-topic = [
    "bertopic>=0.15.0",
    "gensim>=4.3.0"
]
split-all = [
    "semantica[split-tiktoken,split-community,split-topic]"
]
graph-neo4j = [
    "neo4j>=5.0.0"
]
graph-falkordb = [
    "falkordb>=1.0.0",
    "redis>=4.3.0"
]
graph-amazon-neptune = [
    "boto3>=1.24.0",
    "neo4j>=5.0.0"
]
graph-all = [
    "semantica[graph-neo4j,graph-falkordb,graph-amazon-neptune]"
]
parse-docling = [
    "docling>=1.0.0"
]
all = [
    "semantica[dev,viz,gpu,cloud,monitoring,llm-all,models-huggingface,split-all,graph-all,parse-docling]"
]

[project.scripts]
semantica = "semantica.cli:main"
semantica-server = "semantica.server:main"
semantica-worker = "semantica.worker:main"

[tool.setuptools.packages.find]
where = ["."]
include = ["semantica*"]
exclude = ["tests*", "docs*", "examples*"]

[tool.setuptools.package-data]
semantica = ["*.yaml", "*.yml", "*.json", "*.toml", "*.txt", "*.md"]

[tool.black]
line-length = 88
target-version = ['py38', 'py39', 'py310', 'py311', 'py312']
include = '\.pyi?$'
extend-exclude = '''
/(
  # directories
  \.eggs
  | \.git
  | \.hg
  | \.mypy_cache
  | \.tox
  | \.venv
  | build
  | dist
)/
'''

[tool.isort]
profile = "black"
multi_line_output = 3
line_length = 88
known_first_party = ["semantica"]
known_third_party = ["numpy", "pandas", "scikit-learn", "spacy", "transformers", "torch"]

[tool.mypy]
python_version = "3.9"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
strict_equality = true
show_error_codes = true

[tool.pytest.ini_options]
minversion = "7.0"
addopts = "-ra -q --strict-markers --strict-config"
testpaths = ["tests"]
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
markers = [
    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
    "integration: marks tests as integration tests",
    "unit: marks tests as unit tests",
    "gpu: marks tests that require GPU",
    "cloud: marks tests that require cloud services"
]

[tool.coverage.run]
source = ["semantica"]
omit = [
    "*/tests/*",
    "*/test_*",
    "*/__pycache__/*",
    "*/migrations/*"
]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "if self.debug:",
    "if settings.DEBUG",
    "raise AssertionError",
    "raise NotImplementedError",
    "if 0:",
    "if __name__ == .__main__.:",
    "class .*\\bProtocol\\):",
    "@(abc\\.)?abstractmethod"
]